activity
20122026
most citedMean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

1.6k citations · 2.2k across the 16 of their papers we have counts for

collaborators
Showing 2013Show all

1 paper · 1 filter

cs.LG2013

Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities

Tommi Vatanen, Tapani Raiko, Harri Valpola +1

Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut co…